Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events that happen after a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "after" followed by numeric values, indicating time-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aez
    -0.76
    NRS
    -0.70
    cci
    -0.70
    eto
    -0.67
    odiac
    -0.66
    âĸĪâĸĪâĸĪâĸĪ
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    Mask
    -0.65
    aq
    -0.65
    Davis
    -0.64
    POSITIVE LOGITS
    noon
    1.05
    market
    1.02
    thought
    0.87
     finishing
    0.84
     completing
    0.83
    wards
    0.80
     acquiring
    0.79
    word
    0.78
     supper
    0.77
     inspecting
    0.77
    Act Density 0.108%

    No Known Activations